hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ted Yu (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-3813) Change RPC callQueue size from "handlerCount * MAX_QUEUE_SIZE_PER_HANDLER;"
Date Thu, 19 May 2011 21:43:47 GMT

    [ https://issues.apache.org/jira/browse/HBASE-3813?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13036508#comment-13036508
] 

Ted Yu commented on HBASE-3813:
-------------------------------

w.r.t. moving deserialization overhead into the handlers, it implies we replace the current
call queues with (serialized) parameter queue(s).
Currently we have:
{code}
      if (priorityCallQueue != null && getQosLevel(param) > highPriorityLevel)
{
        priorityCallQueue.put(call);
{code}
getQosLevel() requires deserialized Writable. This means there would be only one parameter
queue after this change.

I assume there would be no call queue because we don't want to keep serialized and unserialized
forms of the same parameter at the same time.

> Change RPC callQueue size from "handlerCount * MAX_QUEUE_SIZE_PER_HANDLER;"
> ---------------------------------------------------------------------------
>
>                 Key: HBASE-3813
>                 URL: https://issues.apache.org/jira/browse/HBASE-3813
>             Project: HBase
>          Issue Type: Bug
>    Affects Versions: 0.92.0
>            Reporter: stack
>            Priority: Critical
>         Attachments: 3813.txt
>
>
> Yesterday debugging w/ Jack we noticed that with few handlers on a big box, he was seeing
stats like this:
> {code}
> 2011-04-21 11:54:49,451 DEBUG org.apache.hadoop.ipc.HBaseServer: Server connection from
X.X.X.X:60931; # active connections: 11; # queued calls: 2500
> {code}
> We had 2500 items in the rpc queue waiting to be processed.
> Turns out he had too few handlers for number of clients (but also, it seems like he figured
hw issues in that his RAM bus was running at 1/4 the rate that it should have been running
at).
> Chatting w/ J-D this morning, he asked if the queues hold 'data'.  The queues hold 'Calls'.
 Calls are the client request.  They contain data.
> Jack had 2500 items queued.  If each item to insert was 1MB, thats 25k * 1MB of memory
that is outside of our generally accounting.
> Currently the queue size is handlers * MAX_QUEUE_SIZE_PER_HANDLER where MAX_QUEUE_SIZE_PER_HANDLER
is hardcoded to be 100.
> If the queue is full we block (LinkedBlockingQueue).
> Going to change the queue size from 100 to 10 by default -- but also will make it configurable
and will doc. this as possible cause of OOME.  Will try it on production here before committing
patch.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message